Mohammed Souidi, A. Habbani, Halim Berradi, Fatna El Mahdi
{"title":"Energy performance of zoning techniques for broadcast processing with reduced redundancy in MANETS","authors":"Mohammed Souidi, A. Habbani, Halim Berradi, Fatna El Mahdi","doi":"10.1145/3289402.3289507","DOIUrl":"https://doi.org/10.1145/3289402.3289507","url":null,"abstract":"Many routing protocols have been proposed in mobile ad hoc and sensor networks in order to optimize their performances. The geographic forwarding rules (GFR) fall within the category of the techniques that reduce the routing overhead. Several zoning techniques have been proposed for the GFR, but only one method have been studied. Performances of this technique have been presented focusing on metrics like throughput, delay and routing overhead. However, the GFR affect also the residual energy of nodes since they decrease the number of retransmissions of broadcast messages. In this paper, we study other zoning techniques focusing on the power consumption of the GFR. We present a comparison analysis of energy usage of different zoning techniques with two, four and eight zones. We evaluate how the zoning method affects the energy consumption in mobile devices.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128406121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Green Data warehouse Design and Exploitation","authors":"Khadija Letrache, Omar El Beggar, M. Ramdani","doi":"10.1145/3289402.3289529","DOIUrl":"https://doi.org/10.1145/3289402.3289529","url":null,"abstract":"In the last few years, the environment protection has become a reel concern in all areas. The \"Green\" label is thus widely used by commercials to glamorize their products, while in practice, this aspect is still neglected. Even in IT domains, the Green initiative is not only advocated in hardware manufacturing and exploitation but also in software development. In this case, the challenge is to design and implement efficient and sustainable software that consume low energy and require less hardware while maintaining its performance. In this respect, we propose in this paper an approach to design and exploit green Data warehouse. We also propose several guidelines and best practices to achieve this purpose.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114717401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Text Classification Approach using Parallel Naive Bayes in Big Data Context","authors":"Houda Amazal, M. Ramdani, M. Kissi","doi":"10.1145/3289402.3289536","DOIUrl":"https://doi.org/10.1145/3289402.3289536","url":null,"abstract":"Text classification is a domain that has been inspiring researchers since many years. Indeed, several approaches have been developed in order to find methods that improve the performance of text classification. But in last decades, because of the technological evolution, textual data becomes more and more abundant on the web. So that classical classification methods are unable to process this huge amount of data and consequently cannot produce satisfied results. Thus, new ways have been explored; to overcome the big dimensions of data, it was necessary to reduce the size of the features of documents and use parallel processing. For this, in our work, we developed a Term Frequency- Inverse Document Frequency (TF-IDF) parallel model to save only the most relevant words in documents. Then, we feed the dataset to a parallel Naive Bayes classifier. Both, the TF-IDF parallel model and parallel Naïve Bayes classifier were implemented on Hadoop system using the MapReduce architecture. The experimental results demonstrate the efficiency of the proposed method to improve the classification accuracy.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125374917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","authors":"","doi":"10.1145/3289402","DOIUrl":"https://doi.org/10.1145/3289402","url":null,"abstract":"","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121031854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Categorizing projects for portfolio selection using clustering techniques","authors":"Ghizlane Elbok, A. Berrado","doi":"10.1145/3289402.3289531","DOIUrl":"https://doi.org/10.1145/3289402.3289531","url":null,"abstract":"This work presents a project categorization process that will help practitioner's and decision makers, in a given organization, to group project portfolio components, falling within common strategic orientations. This is a crucial step before they can initiate candidate projects prioritization and selection process based on common criteria. In this regard, we developed an empirically-based categorization approach through clustering techniques where general but most important project attributes are emphasized. It is initiated by considering the organizational strategy and project characteristics, specific to the organization. The suggested approach is then illustrated through the categorization of more than 50 projects in the case of a company operating in the automotive industry.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126398507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fuzzy-Based Mining Framework of Browsing Behavior to Enhance E-commerce Website Performance: Case Study from Kelkoo.com","authors":"Houda Zaim, M. Ramdani, Adil Haddi","doi":"10.1145/3289402.3289528","DOIUrl":"https://doi.org/10.1145/3289402.3289528","url":null,"abstract":"Existing data mining techniques has been used to find out which online products are relevant in terms of having high sales. There has not been much work done to ensure online customer satisfaction by analyzing its click stream data to enhance e-business. This paper thus proposes a fuzzy data mining model for extracting membership functions from navigational data for identifying fuzzy orientation of customer's behavior on the website features. Features selection technique is also applied to properly track and analyze the adequate e-customer's click data. The usefulness of the proposed approach has been studied by applying it to the European leader in e-commerce advertising, \"Kelkoo\" which helps merchants advertise their products to consumers. The results have made possible to propose some improvements of the website's features or to choose the most suited e-commerce advertising website to publish their products.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123457518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Exploring dimensions influencing the usage of Open Government Data portals","authors":"Kawtar Younsi Dahbi, Hind Lamharhar, D. Chiadmi","doi":"10.1145/3289402.3289526","DOIUrl":"https://doi.org/10.1145/3289402.3289526","url":null,"abstract":"Governments are considered as one of the major producers of data. Opening up and publishing this Big Government Data in national portals have significant impact on fostering innovation, improving transparency, public accountability and collaboration. Thus, the expected benefits are hindered by several factors that influence the usage of Open Government Data portals, exploring and investigating these factors is the first step to propose an evaluation approach for OGD portals and promote their usage. In this work, we identified a set of evaluation dimensions that affect OGD portal's usage and fulfillment of users' needs and requirements. According to the identified dimensions, we propose an evaluation of two national OGD portals","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"369 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131785158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hamid Slimani, Oussama Hamal, N. E. Faddouli, S. Bennani, Naila Amrous
{"title":"Semantic recommendation system of digital educational resources","authors":"Hamid Slimani, Oussama Hamal, N. E. Faddouli, S. Bennani, Naila Amrous","doi":"10.1145/3289402.3289513","DOIUrl":"https://doi.org/10.1145/3289402.3289513","url":null,"abstract":"In today's world, information seekers are confronted with a large volume of very heterogeneous and varied data combined with the multilingual, which makes it difficult to find the most relevant digital educational resource that meets the user's needs. These needs are expressed by a query, generally based on keywords. This observation prompted the researchers to exploit other techniques and methods, among which there is the semantic web. In this paper, we propose a bayesian networks-based recommendation system which represents a recommendation activity. Our goal is to propose an approach to the semantic recommendation of digital resources after each query submitted by the user, by means of SPARQL queries that searches in the Linking Open Data (LOD) cloud.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134316664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Big Data Processing using Machine Learning algorithms: MLlib and Mahout Use Case","authors":"Khadija Aziz, Dounia Zaidouni, M. Bellafkih","doi":"10.1145/3289402.3289525","DOIUrl":"https://doi.org/10.1145/3289402.3289525","url":null,"abstract":"Machine learning is a field within artificial intelligence that allows machines to learn on their own from existing information to make predictions or/and decisions. There are three main categories of machine learning techniques: Collaborative filtering (for making recommendations), Clustering (for discovering structure in collections of data) and Classification (form of supervised learning). Machine learning helps users to make better decisions, Machine learning algorithms create patterns based on previous information and use them to design predictive models, then, use this models to obtain predictions about future data. A huge amount of data from several sources need methods and techniques to be processed correctly, in order to exploit this data efficiently, machine learning is a great technology for exploiting the needs in big data analysis. This paper describes the implementation of Apache Spark MLlib and Apache Mahout in order to process Big Data using Machine Learning algorithms. Furthermore, we conduct experimental simulations to show the difference between this two Machine Learning frameworks. Subsequently, we discuss the most striking observations that emerge from the comparison of these technologies through several experimental studies.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124013400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimal resource allocation in wireless systems under quality of service constraint","authors":"Sara Riahi, Azzeddine Riahi","doi":"10.1145/3289402.3289542","DOIUrl":"https://doi.org/10.1145/3289402.3289542","url":null,"abstract":"Optimal exploitation of available resources is one of the most important aspects of modern communication systems. Resource allocation algorithms are used to allocate bits and powers to the subcarriers of a multi-carrier communication system from the knowledge of the channel. The OFDM (Orthogonal Frequency Division Multiplexing) is the combination of OFDM and precoding. The idea is to group subcarriers into subsets using precoding matrices. Each subset uses the energy of its sub-carriers for transmitting a total number of bits greater than the sum of bits that can be transmitted on each subcarrier individually. The role of resource allocation in multi-carrier systems is to optimize either the throughput or robustness of the system. Under the PSD (Power Spectral Density) constraint and for a given error rate, the resource allocation typically gives either the maximum bit rate for a given system margin or the maximum system margin for a target bit rate.","PeriodicalId":199959,"journal":{"name":"Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications","volume":"544 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131743440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}